Despite the impressive generative capabilities of diffusion models existing diffusion model-
based style transfer methods require inference-stage optimization (eg fine-tuning or textual …

Recent years have witnessed remarkable progress in image generation task where users
can create visually astonishing images with high-quality. However exsiting text-to-image …

Despite large-scale diffusion models being highly capable of generating diverse open-world
content, they still struggle to match the photorealism and fidelity of concept-specific …

Diffusion-based text-to-image personalization have achieved great success in generating
subjects specified by users among various contexts. Even though, existing finetuning-based …

Face stylization refers to the transformation of a face into a specific portrait style. However,
current methods require the use of example-based adaptation approaches to fine-tune pre …

This paper proposes an image-vector dual diffusion model for generative layout design.
Distinct from prior efforts that mostly ignore element-level visual information our approach …

Abstract Concept personalization methods enable large text-to-image models to learn
specific subjects (eg objects/poses/3D models) and synthesize renditions in new contexts …

The absence of well-structured large datasets in medical computer vision results in
decreased performance of automated systems and especially of deep learning models …

The rapid development of generative diffusion models has significantly advanced the field of
style transfer. However, most current style transfer methods based on diffusion models …

Representation disentanglement may help AI fundamentally understand the real world and
thus benefit both discrimination and generation tasks. It currently has at least three …